A set of project-specific instructions for changing authentication and authorization in an MCP router. Authentication checks who is connecting; authorization checks what that caller may access.

It is for modifying authentication modes, token verification, audience metadata, OAuth behavior, and related unit tests.

It helps preserve the router’s security boundary, including token handling, secure public binds, and OAuth or JWT settings.

How berntpopp/genefoundry-router configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to berntpopp/genefoundry-router. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/berntpopp/genefoundry-router/main/.claude/skills/auth-change/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/berntpopp/genefoundry-router

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/berntpopp/genefoundry-router/auth-change/github.svg)](https://agentmods.dev/skills/berntpopp/genefoundry-router/auth-change)

Your own site

<a href="https://agentmods.dev/skills/berntpopp/genefoundry-router/auth-change"><img src="https://agentmods.dev/badge/skills/berntpopp/genefoundry-router/auth-change/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/berntpopp/genefoundry-router/auth-change"><img src="https://agentmods.dev/badge/skills/berntpopp/genefoundry-router/auth-change.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 400 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00043	$0.00400
Opus 5	$0.00022	$0.00200
Sonnet 5	$0.00009	$0.00080
Haiku 4.5	$0.00004	$0.00040

Measured 10d ago against content hash c86560c38c77, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

auth-change scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/auth-change/SKILL.md · 23 lines

What it actually says

Auth Change

Follow AGENTS.md first. Auth is the router's trust boundary; ground in docs/SECURITY-ASSESSMENT-2026-06-29.md and the MCP authorization spec.

Workflow

Work in auth.py (verifiers/modes), config.py (GF_AUTH_MODE, GF_ALLOW_INSECURE, JWT/OAuth settings), and cli.py (bind guard) as applicable. Modes: none (dev / loopback), jwt, oauth.
Never forward the caller's token to backends — the enforcement is make_proxy_client() in composition.py (forward_incoming_headers=False); keep tests/unit/test_no_token_passthrough.py green.
Keep the secure-by-default guard: is_insecure_public_bind (in cli.py) refuses GF_AUTH_MODE=none on a non-loopback bind unless GF_ALLOW_INSECURE=true.
Audience binding (RFC 8707): resource_base_url = the audience (…/mcp), not the root base_url; tolerate a duplicated /mcp in the resource (some clients append it). Serve RFC 9728 Protected Resource Metadata + WWW-Authenticate.
For the OAuth proxy, keep a durable client store and skip redundant consent for an already-approved client.
Add / adjust unit tests; run make ci-local.

Common mistakes

Setting resource_base_url to the root base_url (breaks RFC 8707 audience validation).
Relying on the framework default for header forwarding (it forwards the caller token).

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

10d ago First seen · 23 lines · 43 tokens per session scan A c86560c38c77

Subscribe to this mod's changes

auth-change is a skill published in the GitHub repository berntpopp/genefoundry-router (4 stars, last pushed 3d ago), licensed MIT. It adds 43 tokens to every session and 400 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Backend and APIs Security api-gateway bioinformatics claude clinical-genetics fastmcp gateway

adaptyv

How to use the Adaptyv Bio Foundry API and Python SDK for protein experiment design, submission, and results retrieval. Use this skill whenever the user mentions Adaptyv, Foundry API, protein binding assays, protein screening experiments, BLI/SPR assays, thermostability assays, or wants to submit protein sequences for…

K-Dense-AI/scientific-agent-skills · 113 tokens

benchling-integration

Benchling Python SDK and REST API integration for registry entities, inventory, ELN entries, workflows, Benchling Apps, and Data Warehouse queries. Use when automating lab data with benchling-sdk or the v2 API.

K-Dense-AI/scientific-agent-skills · 50 tokens

implementing-api-abuse-detection-with-rate-limiting

Implement API abuse detection using token bucket, sliding window, and adaptive rate limiting algorithms to prevent DDoS, brute force, and credential stuffing attacks.

xalgorix/xalgorix · 43 tokens

implementing-api-gateway-security-controls

Implements security controls at the API gateway layer including authentication enforcement, rate limiting, request validation, IP allowlisting, TLS termination, and threat protection. The engineer configures API gateways (Kong, AWS API Gateway, Azure APIM, Apigee) to act as a centralized security enforcement point…

xalgorix/xalgorix · 106 tokens

implementing-api-schema-validation-security

Implement API schema validation using OpenAPI specifications and JSON Schema to enforce input/output contracts and prevent injection, data exposure, and mass assignment attacks.

xalgorix/xalgorix · 35 tokens

securing-api-gateway-with-aws-waf

Securing API Gateway endpoints with AWS WAF by configuring managed rule groups for OWASP Top 10 protection, creating custom rate limiting rules, implementing bot control, setting up IP reputation filtering, and monitoring WAF metrics for security effectiveness.

xalgorix/xalgorix · 59 tokens

genefoundry-router: Skill for Claude Code